sharkdp/hexyl

A command-line hex viewer

10,086 rs medium
906
Generated Behavioral Tests
99.7%
Best Score
Claude Opus 5 (xhigh)

Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details

21 runs
# Model Score Cost Calls
1 Claude Opus 5 (xhigh) 99.7% $37.26 242 trace →
2 GPT-5.6 Sol (xhigh) 95.9% $5.82 33 trace →
3 Claude Opus 4.8 (xhigh) 95.7% $24.50 157 trace →
4 GPT 5.5 (xhigh) 95.4% $13.44 87 trace →
5 Gemini 3.7 Flash 94.0% $2.19 144 trace →
6 Claude Opus 4.7 (xhigh) 89.3% $23.56 256 trace →
7 Gemini 3.5 Flash 87.2% $10.51 188 trace →
8 GLM-5.2 82.9% $11.68 123 trace →
9 Claude Sonnet 4.6 82.8% $32.57 443 trace →
10 GPT-5.6 Sol 82.2% $1.24 22 trace →
11 Claude Opus 4.7 81.6% $10.35 164 trace →
12 Claude Opus 4.6 81.3% $12.37 236 trace →
13 Gemini 3.6 Flash 76.6% $4.79 129 trace →
14 GPT 5.4 54.1% $0.32 12 trace →
15 Gemini 3 Flash 51.9% $0.45 76 trace →
16 GPT 5.5 (high) 50.7% $3.22 33 trace →
17 GPT 5.5 45.1% $1.07 14 trace →
18 Gemini 3.1 Pro 36.0% $2.46 122 trace →
19 Claude Haiku 4.5 34.1% $0.87 92 trace →
20 GPT 5 mini 7.3% $0.02 13 trace →
21 GPT 5.4 mini 0.0% $0.04 9 trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run